Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    representing or defining concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.92
     você
    0.84
     vocês
    0.76
    you
    0.76
     You
    0.73
     Você
    0.70
    You
    0.70
     kalian
    0.69
     আপনারা
    0.68
    ?),
    0.66
    POSITIVE LOGITS
     representa
    1.03
     representan
    1.00
     rappresenta
    0.96
     represents
    0.95
     represent
    0.95
     remain
    0.93
     representando
    0.91
    representing
    0.91
     representing
    0.91
     rappresent
    0.91
    Act Density 0.173%

    No Known Activations